9 citations · 14 across the 16 of their papers we have counts for
18 papers
Alignment Defends LLMs from Property Inference Attacks
Pengrun Huang, Chhavi Yadav, Ruihan Wu +1
Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties. Recent work has shown that such dataset-l…
Agent Security is a Systems Problem
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda +11
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants…
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
Erchi Wang, Pengrun Huang, Eli Chien +4
Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high b…
Dataset Watermarking with Provable Black-Box Detection
Pengrun Huang, Kamalika Chaudhuri, Yu-Xiang Wang
Large Language Models (LLMs) are often pre-trained and post-trained on vast amounts of loosely curated data, and potentially have been trained on proprietary datasets or the benchm…
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…
Embodied AI Agents: Modeling the World
Pascale Fung, Yoram Bachrach, Asli Celikyilmaz +18
This paper describes our research on AI agents embodied in visual, virtual or physical forms, enabling them to interact with both users and their environments. These agents, which…
Learning-Time Encoding Shapes Unlearning in LLMs
Ruihan Wu, Konstantin Garov, Kamalika Chaudhuri
As large language models (LLMs) are increasingly deployed in the real world, the ability to ``unlearn'', or remove specific pieces of knowledge post hoc, has become essential for a…
Can We Infer Confidential Properties of Training Data from LLMs?
Pengrun Huang, Chhavi Yadav, Kamalika Chaudhuri +1
Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets to support applications in fields such as healthcare, finance, and law. These fine-tuning datas…
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun Hsu +9
Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of i…
ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
Chhavi Yadav, Evan Monroe Laufer, Dan Boneh +1
In principle, explanations are intended as a way to increase trust in machine learning models and are often obligated by regulations. However, many circumstances where these are de…
A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection
Konstantin Garov, Kamalika Chaudhuri
Machine learning algorithms often encounter different or "out-of-distribution" (OOD) data at deployment time, and OOD detection is frequently employed to detect these examples. Whi…
Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
Tatsuki Koga, Ruihan Wu, Zhiyuan Zhang +1
With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outs…
Distribution Learning with Valid Outputs Beyond the Worst-Case
Nick Rittler, Kamalika Chaudhuri
Generative models at times produce "invalid" outputs, such as images with generation artifacts and unnatural sounds. Validity-constrained distribution learning attempts to address…
Influence-based Attributions can be Manipulated
Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri
Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness.…
Evaluating Deep Unlearning in Large Language Models
Ruihan Wu, Chhavi Yadav, Russ Salakhutdinov +1
Machine unlearning has emerged as an important component in developing safe and trustworthy models. Prior work on fact unlearning in LLMs has mostly focused on removing a specified…
On Differentially Private U Statistics
Kamalika Chaudhuri, Po-Ling Loh, Shourya Pandey +1
We consider the problem of privately estimating a parameter , where , , , are i.i.d. data from some distribution and is a p…
Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift
Robi Bhattacharjee, Nick Rittler, Kamalika Chaudhuri
Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training dist…
Better Membership Inference Privacy Measurement through Discrepancy
Ruihan Wu, Pengrun Huang, Kamalika Chaudhuri
Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advanta…